SPORF
SPORF copied to clipboard
neurodata
This is the implementation of Sparse Projection Oblique Randomer Forest
As a quick-fix until we get a `randMat` class. @jovo @falkben @jbrowne6 My suggestions (ranked) are: 1. binnedBaseProjection 2. binnedBaseRandMat 3. binnedBaseWeighted 4. binnedBaseCustom
Just a reminder for @MrAE to double check this. https://github.com/neurodata/RerF/blob/656721031c32028ca32d9c43fc5a2d5ad913dc6f/R-Project/R/RandMat.R#L420
I followed the steps exactly from the README. This is what I get: ``` ** testing if installed package can be loaded Error: package or namespace load failed for ‘rerf’...
**Describe the bug** When in R-RerF and Y happens to be a 1-column matrix or data.frame RerF just crashed and closed my R session. **Fix** Include a check in the...
Different combinations of `max_features` and `feature_combinations` are resulting in segfaults when called from the sklearn class (rerfClassifier). Needs to be reproduced on different systems but known failures in OSX. @MrAE...
@falkben @jbrowne6 When fpRerF in a for loop something bad happens: ```r for(i in 1:10){ X
i never seriously considered defaults for really low dimensions. it occurs to me that it might make sense for mtry to never be much smaller than 100, and rather than...
@falkben related to what you added for sk-learn compatibility.
for instance: `self.estimators_` contains a list of trees in sklearn However, we store multiple trees in each bin, with multiple bins representing the forest. also, trees are interleaved within the...
https://oracle.github.io/Skater/overview.html Can calc feature importance